{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3POLG3WDP77SHWJEGDYWUOE5JH","short_pith_number":"pith:3POLG3WD","schema_version":"1.0","canonical_sha256":"dbdcb36ec37fff23d92430f16a389d49fe0f3270d362b6645aee9d7046fc94fe","source":{"kind":"arxiv","id":"1912.00894","version":2},"attestation_state":"computed","paper":{"title":"On the geometry of Stein variational gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.AP","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"A. Duncan, L. Szpruch, N. Nuesken","submitted_at":"2019-12-02T16:20:05Z","abstract_excerpt":"Bayesian inference problems require sampling or approximating high-dimensional probability distributions. The focus of this paper is on the recently introduced Stein variational gradient descent methodology, a class of algorithms that rely on iterated steepest descent steps with respect to a reproducing kernel Hilbert space norm. This construction leads to interacting particle systems, the mean-field limit of which is a gradient flow on the space of probability distributions equipped with a certain geometrical structure. We leverage this viewpoint to shed some light on the convergence properti"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.00894","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-02T16:20:05Z","cross_cats_sorted":["cs.LG","math.AP","math.ST","stat.TH"],"title_canon_sha256":"25cd99b32000083e2d8aa03363d87438df43f8579c8fd4d2d5c6353cceda8921","abstract_canon_sha256":"7898280d7c011c059ea1969b38b511c0c9e6d1784384bd341ba853c269bfb592"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:41.198349Z","signature_b64":"vo2vJdGaXUJvo9qDaqQD4eDK0LINKH9oa+vccZWRlzcHUlh0KCQvfBvRnsg5uo8CxAZ+aHDDBpeDU6bVnF+ACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbdcb36ec37fff23d92430f16a389d49fe0f3270d362b6645aee9d7046fc94fe","last_reissued_at":"2026-07-05T05:40:41.197814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:41.197814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the geometry of Stein variational gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.AP","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"A. Duncan, L. Szpruch, N. Nuesken","submitted_at":"2019-12-02T16:20:05Z","abstract_excerpt":"Bayesian inference problems require sampling or approximating high-dimensional probability distributions. The focus of this paper is on the recently introduced Stein variational gradient descent methodology, a class of algorithms that rely on iterated steepest descent steps with respect to a reproducing kernel Hilbert space norm. This construction leads to interacting particle systems, the mean-field limit of which is a gradient flow on the space of probability distributions equipped with a certain geometrical structure. We leverage this viewpoint to shed some light on the convergence properti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00894","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.00894/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.00894","created_at":"2026-07-05T05:40:41.197879+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00894v2","created_at":"2026-07-05T05:40:41.197879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00894","created_at":"2026-07-05T05:40:41.197879+00:00"},{"alias_kind":"pith_short_12","alias_value":"3POLG3WDP77S","created_at":"2026-07-05T05:40:41.197879+00:00"},{"alias_kind":"pith_short_16","alias_value":"3POLG3WDP77SHWJE","created_at":"2026-07-05T05:40:41.197879+00:00"},{"alias_kind":"pith_short_8","alias_value":"3POLG3WD","created_at":"2026-07-05T05:40:41.197879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02102","citing_title":"Accelerated Information Gradient flow","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3POLG3WDP77SHWJEGDYWUOE5JH","json":"https://pith.science/pith/3POLG3WDP77SHWJEGDYWUOE5JH.json","graph_json":"https://pith.science/api/pith-number/3POLG3WDP77SHWJEGDYWUOE5JH/graph.json","events_json":"https://pith.science/api/pith-number/3POLG3WDP77SHWJEGDYWUOE5JH/events.json","paper":"https://pith.science/paper/3POLG3WD"},"agent_actions":{"view_html":"https://pith.science/pith/3POLG3WDP77SHWJEGDYWUOE5JH","download_json":"https://pith.science/pith/3POLG3WDP77SHWJEGDYWUOE5JH.json","view_paper":"https://pith.science/paper/3POLG3WD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00894&json=true","fetch_graph":"https://pith.science/api/pith-number/3POLG3WDP77SHWJEGDYWUOE5JH/graph.json","fetch_events":"https://pith.science/api/pith-number/3POLG3WDP77SHWJEGDYWUOE5JH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3POLG3WDP77SHWJEGDYWUOE5JH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3POLG3WDP77SHWJEGDYWUOE5JH/action/storage_attestation","attest_author":"https://pith.science/pith/3POLG3WDP77SHWJEGDYWUOE5JH/action/author_attestation","sign_citation":"https://pith.science/pith/3POLG3WDP77SHWJEGDYWUOE5JH/action/citation_signature","submit_replication":"https://pith.science/pith/3POLG3WDP77SHWJEGDYWUOE5JH/action/replication_record"}},"created_at":"2026-07-05T05:40:41.197879+00:00","updated_at":"2026-07-05T05:40:41.197879+00:00"}